© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12322
    Prev
    Next
    INDEX
    Explanations

    invalid url or website

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Поэтому
    -1.14
     Therefore
    -0.92
     That
    -0.90
     up
    -0.90
    azz
    -0.88
     Also
    -0.83
     boring
    -0.82
     For
    -0.81
    ish
    -0.80
    発展
    -0.78
    POSITIVE LOGITS
     fallecido
    1.10
    INVALID
    1.06
     Aucun
    1.05
    UrlResolution
    1.02
     olmayan
    1.00
    らかに
    0.98
     epä
    0.93
     zbyt
    0.93
     quá
    0.91
     Produit
    0.88
    Activations Density 0.051%

    No Known Activations